© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12362
    Prev
    Next
    INDEX
    Explanations

    t-stat, z-score, chi-square

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĭ¦è¾£
    -0.09
    akhir
    -0.09
    ewis
    -0.08
    ä¸įå¦ĤæĦı
    -0.08
    å°ijåħĪ
    -0.08
    odore
    -0.08
    ëĦIJ
    -0.08
     hinweg
    -0.08
    åĬłå¼ºåŃ¦ä¹ł
    -0.08
    祸é¦ĸ
    -0.08
    POSITIVE LOGITS
    -based
    0.08
    å¼ı
    0.07
    åŀĭ
    0.07
    olino
    0.07
    [/
    0.06
    å±ķå¼Ģåħ¨æĸĩ
    0.06
    udu
    0.06
    pear
    0.06
    åĨĴ
    0.06
    æı
    0.06
    Activations Density 0.010%

    No Known Activations